This website uses cookies

This websites contains videos from YouTube. This company uses cookies (third party cookies). If you do not want them to use these cookies, you can indicate so here. However, this does mean that you will not be able to watch videos on this website. We also make use of our own cookies in order to improve our website. We don’t share our data with other parties. Read more about our cookie policy

This website uses cookies to enable video and to improve the user experience. If you do not want to accept these cookies, indicate so here. Read more about our cookie policy

Ga direct naar de inhoud, het hoofdmenu, het servicemenu of het zoekveld.

Psychosocial Research and Epidemiology: Michael Hauptmann


Michael Hauptmann, Ph.D.

About Michael Hauptmann

The Biostatistics group in the Division of Psychosocial Research and Epidemiology concentrates on methodological and statistical research and collaborates on several international epidemiological and clinical studies with cancer, cardiovascular disease and psychological outcomes. The group also runs the Biostatistics Center which provides statistical expertise to investigators in both the Netherlands Cancer Institute as well as the Antoni van Leeuwenhoek hospital on diverse topics from all areas of biomedical cancer research. The main research interests are as follows.

Statistical methods for the evaluation of health effects from medical radiation exposure

Incorporation of dose distributions is currently not standard in epidemiologic studies of radiotherapy-related second cancer risk. It is expected to yield more efficient and less biased estimates of the dose-response relationship as well as better risk predictions for clinical use. We characterize statistical methods incorporating dose distributions in the organ at risk for a second tumor with regard to efficiency and bias, and describe risk predictions for second cancers following current radiotherapy, calculated by these statistical methods.

In a large retrospective cohort study of children who underwent a computed tomography (CT) scan, we evaluate subsequent risk of cancer due to the radiation exposure. Within the European EPI-CT and MEDIRAD consortia, pooled data form several European countries are jointly analyzed.

Design and statistical analysis of clinical studies for predictive marker evaluation

We assess statistical designs and methods for the evaluation of predictive markers in observational clinical studies or trials with archived specimens. The designs include case-only and hybrid approaches, and we employ additive and multiplicative models. We investigate the required sample size and statistical power as well as other operational characteristics based on simulated data and application to data from breast cancer trials.

Prediction of risks for cancer and cardiovascular disease among cancer survivors

Statistical methods are investigated to jointly use cohort and case-control data for risk prediction, to validate predictions, and to tailor the released information to the personal risk perception of the patient or the doctor.

Evaluating latency of chronic exposures

If exposure data in an epidemiologic study are available as an exposure history (e.g., annual average intensities), a latency function can be estimated describing the relative risk per unit exposure by time since exposure (Hauptmann et al. 2000). As an example, consider lung cancer mortality and occupational exposure to radon gas from a study of Colorado Plateau Uranium Miners (Hauptmann et al. 2001). Click here for EPICURE code for fitting latency models using B-splines for case-control data (conditional/unconditional logistic regression) or cohort data (Cox regression).

Basic Medical Statistics Course

The Biostatistics group offers the Basic Medical Statistics Course annually. This full week course explains statistical techniques for the evaluation of biomedical data. It provides an introduction into design aspects, methods of summarizing and presenting data, estimation, confidence intervals and hypothesis testing, including multivariable regression methods for the assessment of association. For more information, click here.


Jozwiak, Katarzyna.JPG

Dr. Katarzyna Jozwiak



Dr. Katarzyna Jozwiak obtained a Master's degree in Applied Mathematics from Delft University in 2008, and in Econometrics and Computer Science from the University of Zielona Góra, Poland, in 2009. As a graduate student in Applied Statistics at Utrecht University, she investigated optimal designs of trials with discrete-time survival endpoints and completed her PhD in 2013. After a brief period as software developer at Utrecht University, Dr. Jozwiak joined the Netherlands Cancer Institute in Amsterdam, where she is a statistical consultant for clinicians and other researchers of the Institute and the Antoni van Leeuwenhoek hospital.

Close this window
Zavrakidis, John

John Zavrakidis



Mr John Zavrakidis obtained his Master's degree in Statistical Science for the Life and Behavioral Sciences from Leiden University in 2017. His master thesis focused on investigating  proper combination of multiple imputation and cross-validation in calibration of Cox regression model. In the summer of 2017, Mr Zavrakidis  joined the Netherlands Cancer Institute in Amsterdam, where he works as a junior researcher. His main task  is to  develop an infrastructure for optimal design and innovative statistical analysis of animal studies conducted at the NKI.

Close this window
Stram, Douglas

Douglas Stram

PhD student


Mr Douglas Stram received his master's degree in Biostatistics from the University of Southern California in 2017. His master's thesis work involved developing a risk factor model for the prevalence of diabetic retinopathy among Chinese Americans, using data from a population-based eye health study conducted in Monterey Park, California. He joined the Netherlands Cancer Institute in September 2017 as a PhD student. His project involves developing and characterizing statistical methods for the efficient identification of predictive biomarkers in cancer, in particular the use of case-only and additive-interaction time-to-event models.

Close this window
Roberti, Sander

Sander Roberti

PhD student


Mr Sander Roberti obtained a Master's degree in Mathematics from Radboud University Nijmegen in 2017. His master's thesis compared different statistical methods for analysing the treatment effect using clinical trials with multiple post-treatment measurements. In December 2017, he joined the Netherlands Cancer Institute as a PhD student. His project focuses on developing methods to assess the cancer risk from therapeutic radiation exposure, incorporating data on the spatial distribution of the radiation dose in the target organ. 

Close this window

Recent publications View All Publications

  • Increased pancreatic cancer risk following radiotherapy for testicular cancer.

    Br J Cancer. 2016 Sep 27;115(7):901-8. doi:10.1038/bjc.2016.272

    Hauptmann M, Børge Johannesen T, Gilbert ES, Stovall M, van Leeuwen FE, Rajaraman P, Smith SA, Weathers RE, Aleman BM, Andersson M,...

    Link to PubMed
  • Ovarian Stimulation for In Vitro Fertilization and Long-term Risk of Breast Cancer

    JAMA. 2016 Jul 19;316(3):300-12. doi: 10.1001/jama.2016.9389.

    van den Belt-Dusebout AW, Spaan M, Lambalk CB, Kortman M, Laven JS, van Santbrink EJ, van der Westerlaken LA, Cohlen BJ, Braat DD, Smeenk...

    Link to PubMed


  • Office manager

    Karin Roede & Daniëlle Groenewegen

  • E-mail

  • Telephone Number

    0031 20 512 2480



'Research for the benefit of cancer patients'

Support us
Share this page